diff options
| author | Sergey Sharybin <sergey.vfx@gmail.com> | 2017-05-02 16:03:51 +0300 |
|---|---|---|
| committer | Sergey Sharybin <sergey.vfx@gmail.com> | 2017-05-02 16:03:51 +0300 |
| commit | 4384a7cf463eedea83179da80bbe12ff7d55578a (patch) | |
| tree | 75d663ff30399e595a3f0c5515f790788a41dddd | |
| parent | 4174e533c001367b0ef391b72baa5b07cb517ce8 (diff) | |
Cycles: Fix CUDA split kernel
Global size y needs to be a multiple of 16.
| -rw-r--r-- | intern/cycles/device/device_cuda.cpp | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/intern/cycles/device/device_cuda.cpp b/intern/cycles/device/device_cuda.cpp index acfb3e1d8f4..a971170318e 100644 --- a/intern/cycles/device/device_cuda.cpp +++ b/intern/cycles/device/device_cuda.cpp @@ -1634,7 +1634,8 @@ int2 CUDASplitKernel::split_kernel_global_size(device_memory& kg, device_memory& << string_human_readable_size(free) << ")."; size_t num_elements = max_elements_for_max_buffer_size(kg, data, free / 2); - int2 global_size = make_int2(round_down((int)sqrt(num_elements), 32), (int)sqrt(num_elements)); + size_t side = round_down((int)sqrt(num_elements), 32); + int2 global_size = make_int2(side, round_down(num_elements / side, 16)); VLOG(1) << "Global size: " << global_size << "."; return global_size; } |